On Cardinality Estimation Protocols for Wireless Sensor Networks

In this article we address the problem of estimating a size of wireless sensor networks (WSNs). We restrict our attention to sensors with very limited storage capabilities. The problem arises when sensors have to quickly obtain approximate size of the network to use algorithms which require such information. Another application area is the problem of counting the number of different objects (e.g. people in public bus transportation) and use of such information to optimize the routes and frequency of buses. In this paper we present two-phase probabilistic algorithm based on order statistics and balls-bins model which effectively solves the presented problem.